* Copyright (C) 1991, 1992 Linus Torvalds
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/mman.h>
-#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/prctl.h>
#include <linux/highuid.h>
#include <linux/fs.h>
+#include <linux/kmod.h>
#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.h>
#include <linux/ptrace.h>
#include <linux/fs_struct.h>
#include <linux/gfp.h>
+#include <linux/syscore_ops.h>
+#include <linux/version.h>
+#include <linux/ctype.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
#include <linux/kprobes.h>
#include <linux/user_namespace.h>
+#include <linux/kmsg_dump.h>
+/* Move somewhere else to avoid recompiling? */
+#include <generated/utsrelease.h>
+
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/unistd.h>
void (*pm_power_off_prepare)(void);
+/*
+ * Returns true if current's euid is same as p's uid or euid,
+ * or has CAP_SYS_NICE to p's user_ns.
+ *
+ * Called with rcu_read_lock, creds are safe
+ */
+static bool set_one_prio_perm(struct task_struct *p)
+{
+ const struct cred *cred = current_cred(), *pcred = __task_cred(p);
+
+ if (pcred->user->user_ns == cred->user->user_ns &&
+ (pcred->uid == cred->euid ||
+ pcred->euid == cred->euid))
+ return true;
+ if (ns_capable(pcred->user->user_ns, CAP_SYS_NICE))
+ return true;
+ return false;
+}
+
/*
* set the priority of a task
* - the caller must hold the RCU read lock
*/
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
- const struct cred *cred = current_cred(), *pcred = __task_cred(p);
int no_nice;
- if (pcred->uid != cred->euid &&
- pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
+ if (!set_one_prio_perm(p)) {
error = -EPERM;
goto out;
}
*/
void emergency_restart(void)
{
+ kmsg_dump(KMSG_DUMP_EMERG);
machine_emergency_restart();
}
EXPORT_SYMBOL_GPL(emergency_restart);
{
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
+ usermodehelper_disable();
device_shutdown();
- sysdev_shutdown();
+ syscore_shutdown();
+}
+
+/**
+ * register_reboot_notifier - Register function to be called at reboot time
+ * @nb: Info about notifier function to be called
+ *
+ * Registers a function with the list of functions
+ * to be called at reboot time.
+ *
+ * Currently always returns zero, as blocking_notifier_chain_register()
+ * always returns zero.
+ */
+int register_reboot_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&reboot_notifier_list, nb);
+}
+EXPORT_SYMBOL(register_reboot_notifier);
+
+/**
+ * unregister_reboot_notifier - Unregister previously registered reboot notifier
+ * @nb: Hook to be unregistered
+ *
+ * Unregisters a previously registered reboot
+ * notifier function.
+ *
+ * Returns zero on success, or %-ENOENT on failure.
+ */
+int unregister_reboot_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
}
+EXPORT_SYMBOL(unregister_reboot_notifier);
/**
* kernel_restart - reboot the system
printk(KERN_EMERG "Restarting system.\n");
else
printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
+ kmsg_dump(KMSG_DUMP_RESTART);
machine_restart(cmd);
}
EXPORT_SYMBOL_GPL(kernel_restart);
blocking_notifier_call_chain(&reboot_notifier_list,
(state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
system_state = state;
+ usermodehelper_disable();
device_shutdown();
}
/**
void kernel_halt(void)
{
kernel_shutdown_prepare(SYSTEM_HALT);
- sysdev_shutdown();
+ syscore_shutdown();
printk(KERN_EMERG "System halted.\n");
+ kmsg_dump(KMSG_DUMP_HALT);
machine_halt();
}
if (pm_power_off_prepare)
pm_power_off_prepare();
disable_nonboot_cpus();
- sysdev_shutdown();
+ syscore_shutdown();
printk(KERN_EMERG "Power down.\n");
+ kmsg_dump(KMSG_DUMP_POWEROFF);
machine_power_off();
}
EXPORT_SYMBOL_GPL(kernel_power_off);
if (rgid != (gid_t) -1) {
if (old->gid == rgid ||
old->egid == rgid ||
- capable(CAP_SETGID))
+ nsown_capable(CAP_SETGID))
new->gid = rgid;
else
goto error;
if (old->gid == egid ||
old->egid == egid ||
old->sgid == egid ||
- capable(CAP_SETGID))
+ nsown_capable(CAP_SETGID))
new->egid = egid;
else
goto error;
old = current_cred();
retval = -EPERM;
- if (capable(CAP_SETGID))
+ if (nsown_capable(CAP_SETGID))
new->gid = new->egid = new->sgid = new->fsgid = gid;
else if (gid == old->gid || gid == old->sgid)
new->egid = new->fsgid = gid;
if (!new_user)
return -EAGAIN;
+ /*
+ * We don't fail in case of NPROC limit excess here because too many
+ * poorly written programs don't check set*uid() return code, assuming
+ * it never fails if called by root. We may still enforce NPROC limit
+ * for programs doing set*uid()+execve() by harmlessly deferring the
+ * failure to the execve() stage.
+ */
if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
- new_user != INIT_USER) {
- free_uid(new_user);
- return -EAGAIN;
- }
+ new_user != INIT_USER)
+ current->flags |= PF_NPROC_EXCEEDED;
+ else
+ current->flags &= ~PF_NPROC_EXCEEDED;
free_uid(new->user);
new->user = new_user;
new->uid = ruid;
if (old->uid != ruid &&
old->euid != ruid &&
- !capable(CAP_SETUID))
+ !nsown_capable(CAP_SETUID))
goto error;
}
if (old->uid != euid &&
old->euid != euid &&
old->suid != euid &&
- !capable(CAP_SETUID))
+ !nsown_capable(CAP_SETUID))
goto error;
}
old = current_cred();
retval = -EPERM;
- if (capable(CAP_SETUID)) {
+ if (nsown_capable(CAP_SETUID)) {
new->suid = new->uid = uid;
if (uid != old->uid) {
retval = set_user(new);
old = current_cred();
retval = -EPERM;
- if (!capable(CAP_SETUID)) {
+ if (!nsown_capable(CAP_SETUID)) {
if (ruid != (uid_t) -1 && ruid != old->uid &&
ruid != old->euid && ruid != old->suid)
goto error;
old = current_cred();
retval = -EPERM;
- if (!capable(CAP_SETGID)) {
+ if (!nsown_capable(CAP_SETGID)) {
if (rgid != (gid_t) -1 && rgid != old->gid &&
rgid != old->egid && rgid != old->sgid)
goto error;
if (uid == old->uid || uid == old->euid ||
uid == old->suid || uid == old->fsuid ||
- capable(CAP_SETUID)) {
+ nsown_capable(CAP_SETUID)) {
if (uid != old_fsuid) {
new->fsuid = uid;
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
if (gid == old->gid || gid == old->egid ||
gid == old->sgid || gid == old->fsgid ||
- capable(CAP_SETGID)) {
+ nsown_capable(CAP_SETGID)) {
if (gid != old_fsgid) {
new->fsgid = gid;
goto change_okay;
pgid = pid;
if (pgid < 0)
return -EINVAL;
+ rcu_read_lock();
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
+ rcu_read_unlock();
return err;
}
err = session;
out:
write_unlock_irq(&tasklist_lock);
- if (err > 0)
+ if (err > 0) {
proc_sid_connector(group_leader);
+ sched_autogroup_create_attach(group_leader);
+ }
return err;
}
#define override_architecture(name) 0
#endif
+/*
+ * Work around broken programs that cannot handle "Linux 3.0".
+ * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ */
+static int override_release(char __user *release, int len)
+{
+ int ret = 0;
+ char buf[65];
+
+ if (current->personality & UNAME26) {
+ char *rest = UTS_RELEASE;
+ int ndots = 0;
+ unsigned v;
+
+ while (*rest) {
+ if (*rest == '.' && ++ndots >= 3)
+ break;
+ if (!isdigit(*rest) && *rest != '.')
+ break;
+ rest++;
+ }
+ v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+ snprintf(buf, len, "2.6.%u%s", v, rest);
+ ret = copy_to_user(release, buf, len);
+ }
+ return ret;
+}
+
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
{
int errno = 0;
errno = -EFAULT;
up_read(&uts_sem);
+ if (!errno && override_release(name->release, sizeof(name->release)))
+ errno = -EFAULT;
if (!errno && override_architecture(name))
errno = -EFAULT;
return errno;
error = -EFAULT;
up_read(&uts_sem);
+ if (!error && override_release(name->release, sizeof(name->release)))
+ error = -EFAULT;
if (!error && override_architecture(name))
error = -EFAULT;
return error;
if (!error && override_architecture(name))
error = -EFAULT;
+ if (!error && override_release(name->release, sizeof(name->release)))
+ error = -EFAULT;
return error ? -EFAULT : 0;
}
#endif
int errno;
char tmp[__NEW_UTS_LEN];
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
+
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
down_write(&uts_sem);
memset(u->nodename + len, 0, sizeof(u->nodename) - len);
errno = 0;
}
+ uts_proc_notify(UTS_PROC_HOSTNAME);
up_write(&uts_sem);
return errno;
}
int errno;
char tmp[__NEW_UTS_LEN];
- if (!capable(CAP_SYS_ADMIN))
+ if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
memset(u->domainname + len, 0, sizeof(u->domainname) - len);
errno = 0;
}
+ uts_proc_notify(UTS_PROC_DOMAINNAME);
up_write(&uts_sem);
return errno;
}
SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
{
- if (resource >= RLIM_NLIMITS)
- return -EINVAL;
- else {
- struct rlimit value;
- task_lock(current->group_leader);
- value = current->signal->rlim[resource];
- task_unlock(current->group_leader);
- return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
- }
+ struct rlimit value;
+ int ret;
+
+ ret = do_prlimit(current, resource, NULL, &value);
+ if (!ret)
+ ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
+
+ return ret;
}
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
#endif
-SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+static inline bool rlim64_is_infinity(__u64 rlim64)
{
- struct rlimit new_rlim, *old_rlim;
- int retval;
+#if BITS_PER_LONG < 64
+ return rlim64 >= ULONG_MAX;
+#else
+ return rlim64 == RLIM64_INFINITY;
+#endif
+}
+
+static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64)
+{
+ if (rlim->rlim_cur == RLIM_INFINITY)
+ rlim64->rlim_cur = RLIM64_INFINITY;
+ else
+ rlim64->rlim_cur = rlim->rlim_cur;
+ if (rlim->rlim_max == RLIM_INFINITY)
+ rlim64->rlim_max = RLIM64_INFINITY;
+ else
+ rlim64->rlim_max = rlim->rlim_max;
+}
+
+static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim)
+{
+ if (rlim64_is_infinity(rlim64->rlim_cur))
+ rlim->rlim_cur = RLIM_INFINITY;
+ else
+ rlim->rlim_cur = (unsigned long)rlim64->rlim_cur;
+ if (rlim64_is_infinity(rlim64->rlim_max))
+ rlim->rlim_max = RLIM_INFINITY;
+ else
+ rlim->rlim_max = (unsigned long)rlim64->rlim_max;
+}
+
+/* make sure you are allowed to change @tsk limits before calling this */
+int do_prlimit(struct task_struct *tsk, unsigned int resource,
+ struct rlimit *new_rlim, struct rlimit *old_rlim)
+{
+ struct rlimit *rlim;
+ int retval = 0;
if (resource >= RLIM_NLIMITS)
return -EINVAL;
- if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
- return -EFAULT;
- if (new_rlim.rlim_cur > new_rlim.rlim_max)
- return -EINVAL;
- old_rlim = current->signal->rlim + resource;
- if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
- !capable(CAP_SYS_RESOURCE))
- return -EPERM;
- if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
- return -EPERM;
-
- retval = security_task_setrlimit(current, resource, &new_rlim);
- if (retval)
- return retval;
-
- if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
- /*
- * The caller is asking for an immediate RLIMIT_CPU
- * expiry. But we use the zero value to mean "it was
- * never set". So let's cheat and make it one second
- * instead
- */
- new_rlim.rlim_cur = 1;
+ if (new_rlim) {
+ if (new_rlim->rlim_cur > new_rlim->rlim_max)
+ return -EINVAL;
+ if (resource == RLIMIT_NOFILE &&
+ new_rlim->rlim_max > sysctl_nr_open)
+ return -EPERM;
}
- task_lock(current->group_leader);
- *old_rlim = new_rlim;
- task_unlock(current->group_leader);
-
- if (resource != RLIMIT_CPU)
+ /* protect tsk->signal and tsk->sighand from disappearing */
+ read_lock(&tasklist_lock);
+ if (!tsk->sighand) {
+ retval = -ESRCH;
goto out;
+ }
+
+ rlim = tsk->signal->rlim + resource;
+ task_lock(tsk->group_leader);
+ if (new_rlim) {
+ /* Keep the capable check against init_user_ns until
+ cgroups can contain all limits */
+ if (new_rlim->rlim_max > rlim->rlim_max &&
+ !capable(CAP_SYS_RESOURCE))
+ retval = -EPERM;
+ if (!retval)
+ retval = security_task_setrlimit(tsk->group_leader,
+ resource, new_rlim);
+ if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) {
+ /*
+ * The caller is asking for an immediate RLIMIT_CPU
+ * expiry. But we use the zero value to mean "it was
+ * never set". So let's cheat and make it one second
+ * instead
+ */
+ new_rlim->rlim_cur = 1;
+ }
+ }
+ if (!retval) {
+ if (old_rlim)
+ *old_rlim = *rlim;
+ if (new_rlim)
+ *rlim = *new_rlim;
+ }
+ task_unlock(tsk->group_leader);
/*
* RLIMIT_CPU handling. Note that the kernel fails to return an error
* very long-standing error, and fixing it now risks breakage of
* applications, so we live with it
*/
- if (new_rlim.rlim_cur == RLIM_INFINITY)
- goto out;
-
- update_rlimit_cpu(current, new_rlim.rlim_cur);
+ if (!retval && new_rlim && resource == RLIMIT_CPU &&
+ new_rlim->rlim_cur != RLIM_INFINITY)
+ update_rlimit_cpu(tsk, new_rlim->rlim_cur);
out:
- return 0;
+ read_unlock(&tasklist_lock);
+ return retval;
+}
+
+/* rcu lock must be held */
+static int check_prlimit_permission(struct task_struct *task)
+{
+ const struct cred *cred = current_cred(), *tcred;
+
+ if (current == task)
+ return 0;
+
+ tcred = __task_cred(task);
+ if (cred->user->user_ns == tcred->user->user_ns &&
+ (cred->uid == tcred->euid &&
+ cred->uid == tcred->suid &&
+ cred->uid == tcred->uid &&
+ cred->gid == tcred->egid &&
+ cred->gid == tcred->sgid &&
+ cred->gid == tcred->gid))
+ return 0;
+ if (ns_capable(tcred->user->user_ns, CAP_SYS_RESOURCE))
+ return 0;
+
+ return -EPERM;
+}
+
+SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
+ const struct rlimit64 __user *, new_rlim,
+ struct rlimit64 __user *, old_rlim)
+{
+ struct rlimit64 old64, new64;
+ struct rlimit old, new;
+ struct task_struct *tsk;
+ int ret;
+
+ if (new_rlim) {
+ if (copy_from_user(&new64, new_rlim, sizeof(new64)))
+ return -EFAULT;
+ rlim64_to_rlim(&new64, &new);
+ }
+
+ rcu_read_lock();
+ tsk = pid ? find_task_by_vpid(pid) : current;
+ if (!tsk) {
+ rcu_read_unlock();
+ return -ESRCH;
+ }
+ ret = check_prlimit_permission(tsk);
+ if (ret) {
+ rcu_read_unlock();
+ return ret;
+ }
+ get_task_struct(tsk);
+ rcu_read_unlock();
+
+ ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
+ old_rlim ? &old : NULL);
+
+ if (!ret && old_rlim) {
+ rlim_to_rlim64(&old, &old64);
+ if (copy_to_user(old_rlim, &old64, sizeof(old64)))
+ ret = -EFAULT;
+ }
+
+ put_task_struct(tsk);
+ return ret;
+}
+
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+ struct rlimit new_rlim;
+
+ if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+ return -EFAULT;
+ return do_prlimit(current, resource, &new_rlim, NULL);
}
/*
unsigned long maxrss = 0;
memset((char *) r, 0, sizeof *r);
- utime = stime = cputime_zero;
+ utime = stime = 0;
if (who == RUSAGE_THREAD) {
task_times(current, &utime, &stime);
case RUSAGE_SELF:
thread_group_times(p, &tgutime, &tgstime);
- utime = cputime_add(utime, tgutime);
- stime = cputime_add(stime, tgstime);
+ utime += tgutime;
+ stime += tgstime;
r->ru_nvcsw += p->signal->nvcsw;
r->ru_nivcsw += p->signal->nivcsw;
r->ru_minflt += p->signal->min_flt;
return mask;
}
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int prctl_set_mm(int opt, unsigned long addr,
+ unsigned long arg4, unsigned long arg5)
+{
+ unsigned long rlim = rlimit(RLIMIT_DATA);
+ unsigned long vm_req_flags;
+ unsigned long vm_bad_flags;
+ struct vm_area_struct *vma;
+ int error = 0;
+ struct mm_struct *mm = current->mm;
+
+ if (arg4 | arg5)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (addr >= TASK_SIZE)
+ return -EINVAL;
+
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, addr);
+
+ if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
+ /* It must be existing VMA */
+ if (!vma || vma->vm_start > addr)
+ goto out;
+ }
+
+ error = -EINVAL;
+ switch (opt) {
+ case PR_SET_MM_START_CODE:
+ case PR_SET_MM_END_CODE:
+ vm_req_flags = VM_READ | VM_EXEC;
+ vm_bad_flags = VM_WRITE | VM_MAYSHARE;
+
+ if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
+ (vma->vm_flags & vm_bad_flags))
+ goto out;
+
+ if (opt == PR_SET_MM_START_CODE)
+ mm->start_code = addr;
+ else
+ mm->end_code = addr;
+ break;
+
+ case PR_SET_MM_START_DATA:
+ case PR_SET_MM_END_DATA:
+ vm_req_flags = VM_READ | VM_WRITE;
+ vm_bad_flags = VM_EXEC | VM_MAYSHARE;
+
+ if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
+ (vma->vm_flags & vm_bad_flags))
+ goto out;
+
+ if (opt == PR_SET_MM_START_DATA)
+ mm->start_data = addr;
+ else
+ mm->end_data = addr;
+ break;
+
+ case PR_SET_MM_START_STACK:
+
+#ifdef CONFIG_STACK_GROWSUP
+ vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP;
+#else
+ vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
+#endif
+ if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
+ goto out;
+
+ mm->start_stack = addr;
+ break;
+
+ case PR_SET_MM_START_BRK:
+ if (addr <= mm->end_data)
+ goto out;
+
+ if (rlim < RLIM_INFINITY &&
+ (mm->brk - addr) +
+ (mm->end_data - mm->start_data) > rlim)
+ goto out;
+
+ mm->start_brk = addr;
+ break;
+
+ case PR_SET_MM_BRK:
+ if (addr <= mm->end_data)
+ goto out;
+
+ if (rlim < RLIM_INFINITY &&
+ (addr - mm->start_brk) +
+ (mm->end_data - mm->start_data) > rlim)
+ goto out;
+
+ mm->brk = addr;
+ break;
+
+ default:
+ error = -EINVAL;
+ goto out;
+ }
+
+ error = 0;
+
+out:
+ up_read(&mm->mmap_sem);
+
+ return error;
+}
+#else /* CONFIG_CHECKPOINT_RESTORE */
+static int prctl_set_mm(int opt, unsigned long addr,
+ unsigned long arg4, unsigned long arg5)
+{
+ return -EINVAL;
+}
+#endif
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
sizeof(me->comm) - 1) < 0)
return -EFAULT;
set_task_comm(me, comm);
+ proc_comm_connector(me);
return 0;
case PR_GET_NAME:
get_task_comm(comm, me);
else
error = PR_MCE_KILL_DEFAULT;
break;
+ case PR_SET_MM:
+ error = prctl_set_mm(arg2, arg3, arg4, arg5);
+ break;
default:
error = -EINVAL;
break;
Code Review / linux-2.6.git / blobdiff